© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95653
    Prev
    Next
    INDEX
    Explanations

    settings and options

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects section headings or topic labels (short, capitalized phrases often followed by a colon) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    This
    -1.23
    ͌
    -1.02
    w
    -1.00
    ᴘ
    -1.00
    죽
    -0.97
    ̓
    -0.96
     Want
    -0.96
    𝐱
    -0.96
     partiellement
    -0.95
    ardige
    -0.95
    POSITIVE LOGITS
     and
    2.03
     types
    1.33
     často
    1.26
    の種類
    1.20
     choice
    1.16
     should
    1.14
    และ
    1.13
     strategy
    1.13
     criteria
    1.12
     touché
    1.08
    Activations Density 0.045%

    No Known Activations